craft-auditlisted

# Craftsman Audit — the production-readiness orchestrator This is the **conductor**, not another peer domain. The ten `craft-*` skills each own one surface (ux, frontend, backend, db, security, infra, observability, testing, lint, ai). This skill stands above them: it looks at the whole project, decides which of those surfaces apply, plans an audit for each, routes the actual findings to the domain skills, and keeps a durable record of what's been audited and what's left — so a large assessment can run across multiple sessions without losing the thread. It does **not** duplicate domain knowledge. To judge the auth layer it loads `craft-security`; the design system, `craft-ux`; static quality gates, `craft-lint`; LLM integrations, `craft-ai`. The orchestrator owns **discovery, applicability, planning, prioritization, and tracking** — the domain skills own the findings. Keeping that boundary is what stops the two from drifting out of sync. Once findings are tracked, the companion action skill `craft-fix` works through the climb sequence — this skill audits and tracks, it does not itself change code. ## Who this is for (read this first — it sets the register) The primary user is the **builder of a cool-but-fragile MVP**: someone who used Claude, Lovable, Replit, or v0 to ship something that *looks* impressive and *works in the demo*, but is nowhere near production-grade — no real error/empty/loading states, no auth worth the name, no observability, AI "slop" patterns, data t